Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1123. Min Range: -3.1123

Max Act: 3.1123. Min Act: -0.0000

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9918. Min Act: -0.0000

Data Index: 295554 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.7948. Min Act: -0.0000

Data Index: 126595 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6395. Min Act: -0.0000

Data Index: 907217 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6191. Min Act: -0.0000

Data Index: 803434 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6765. Min Act: -0.0000

Data Index: 1137991 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6494. Min Act: -0.0000

Data Index: 12467 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6146. Min Act: -0.0000

Data Index: 566409 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.6021. Min Act: -0.0000

Data Index: 975498 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.5864. Min Act: -0.0000

Data Index: 1060166 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.7047. Min Act: -0.0000

Data Index: 413004 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1332996 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.5387. Min Act: -0.0000

Data Index: 405490 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.3524. Min Act: -0.0000

Data Index: 804654 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.4811. Min Act: -0.0000

Data Index: 1136646 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.4444. Min Act: -0.0000

Data Index: 650542 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.4480. Min Act: -0.0000

Data Index: 971803 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.2987. Min Act: -0.0000

Data Index: 88689 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.5295. Min Act: -0.0000

Data Index: 1049809 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.4194. Min Act: -0.0000

Data Index: 1255592 (C4 (Web Text))

Max Activating Token Index: 819